Triple

T15632845
Position Surface form Disambiguated ID Type / Status
Subject Tommy Carcetti E375860 entity
Predicate hasAdvisor P25349 FINISHED
Object Norman Wilson E1174039 NE FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Norman Wilson | Statement: [Tommy Carcetti, hasAdvisor, Norman Wilson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Norman Wilson
Context triple: [Tommy Carcetti, hasAdvisor, Norman Wilson]
  • A. Norman Wilson chosen
    Norman Wilson is a seasoned political operative and advisor known for managing campaigns and navigating the complexities of urban politics.
  • B. Norman Black
    Norman Black is a former American professional basketball player and highly successful coach, best known for his long and decorated career in the Philippine Basketball Association.
  • C. Charles B. Mulvehill
    Charles B. Mulvehill was a film producer best known for his work on the cult classic dark comedy "Harold and Maude."
  • D. Effingham Wilson
    Effingham Wilson was a prominent 19th-century London publisher known for issuing works of literature, radical politics, and social reform.
  • E. Louis D. Wilson
    Louis D. Wilson was a 19th-century North Carolina politician and military officer after whom the city of Wilson, North Carolina, is named.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d85cd035a48190b73d5579ab73969a completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04eb7338881909f3c430bb73f91d1 completed April 16, 2026, 2:51 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff875e49748190a2a4aceb649762b4 completed May 9, 2026, 7:13 p.m.
Created at: April 10, 2026, 4:14 a.m.